claude-code - 💡(How to fix) Fix Bug: claude.ai cowork - "Server is temporarily limiting requests" recurs and blocks conversation continuation [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#58826Fetched 2026-05-14 03:38:30
View on GitHub
Comments
1
Participants
2
Timeline
5
Reactions
0
Timeline (top)
labeled ×4commented ×1
  • Surface: claude.ai cowork sessions (not Claude Code CLI).
  • Filed via Claude Code /anthropic-escalation skill v1.1 because anthropics/claude-code is the only public Anthropic issue intake; no claude.ai-specific public repo exists.
  • Repro: error recurs on continued use of an active cowork session; exact send-count threshold and timing not yet captured.
  • Workaround attempted: re-sending the same message reproduces the error; "restart from an earlier message" does not change throttling state.

If this is the wrong repo for claude.ai cowork issues, please redirect.

Error Message

Inside a claude.ai cowork session, the following error is returned repeatedly when sending a message:

Root Cause

  • Surface: claude.ai cowork sessions (not Claude Code CLI).
  • Filed via Claude Code /anthropic-escalation skill v1.1 because anthropics/claude-code is the only public Anthropic issue intake; no claude.ai-specific public repo exists.
  • Repro: error recurs on continued use of an active cowork session; exact send-count threshold and timing not yet captured.
  • Workaround attempted: re-sending the same message reproduces the error; "restart from an earlier message" does not change throttling state.

Fix Action

Fix / Workaround

  1. Is the cowork-session pathway hitting a tighter server-side rate limit than the standard claude.ai chat surface? If yes, can the limit be raised, or surfaced in the UI with a Retry-After value so the client can back off intelligently?
  2. What triggers this throttle? Per-session message count, total tokens in the cowork context, concurrent cowork participants, or something else? Knowing the trigger lets users self-pace.
  3. Is a fix or mitigation tracked anywhere users can follow? A status-page entry or roadmap item would let affected users avoid re-filing.
  • Surface: claude.ai cowork sessions (not Claude Code CLI).
  • Filed via Claude Code /anthropic-escalation skill v1.1 because anthropics/claude-code is the only public Anthropic issue intake; no claude.ai-specific public repo exists.
  • Repro: error recurs on continued use of an active cowork session; exact send-count threshold and timing not yet captured.
  • Workaround attempted: re-sending the same message reproduces the error; "restart from an earlier message" does not change throttling state.

Code Example

Something went wrong
Try sending your message again. If it keeps happening, share feedback so we can investigate.

API Error: Server is temporarily limiting requests (not your usage limit) - Rate limited
You can restart the conversation from an earlier message.
RAW_BUFFERClick to expand / collapse

Filing from Claude Code on behalf of a user-reported claude.ai web issue. Cowork-session conversations are repeatedly interrupted by a server-side rate-limit error that the user cannot work around from the client side.

Observed behavior

Inside a claude.ai cowork session, the following error is returned repeatedly when sending a message:

Something went wrong
Try sending your message again. If it keeps happening, share feedback so we can investigate.

API Error: Server is temporarily limiting requests (not your usage limit) - Rate limited
You can restart the conversation from an earlier message.

The "(not your usage limit)" parenthetical and "Rate limited" tag indicate server-side throttling rather than account-quota exhaustion. The error recurs across send attempts, blocking forward progress on the cowork conversation. The only client-side option offered is "restart the conversation from an earlier message," which does not address the underlying throttling.

Specific questions / asks

  1. Is the cowork-session pathway hitting a tighter server-side rate limit than the standard claude.ai chat surface? If yes, can the limit be raised, or surfaced in the UI with a Retry-After value so the client can back off intelligently?
  2. What triggers this throttle? Per-session message count, total tokens in the cowork context, concurrent cowork participants, or something else? Knowing the trigger lets users self-pace.
  3. Is a fix or mitigation tracked anywhere users can follow? A status-page entry or roadmap item would let affected users avoid re-filing.

Why this framing

Filing as a new bug rather than a status check: no prior public Anthropic engagement on cowork-session rate limiting has been independently verified at filing time. If a prior thread exists, happy to be redirected to it.

Context

  • Surface: claude.ai cowork sessions (not Claude Code CLI).
  • Filed via Claude Code /anthropic-escalation skill v1.1 because anthropics/claude-code is the only public Anthropic issue intake; no claude.ai-specific public repo exists.
  • Repro: error recurs on continued use of an active cowork session; exact send-count threshold and timing not yet captured.
  • Workaround attempted: re-sending the same message reproduces the error; "restart from an earlier message" does not change throttling state.

If this is the wrong repo for claude.ai cowork issues, please redirect.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix Bug: claude.ai cowork - "Server is temporarily limiting requests" recurs and blocks conversation continuation [1 comments, 2 participants]